Transfer Neural Trees for Heterogeneous Domain Adaptation

Heterogeneous domain adaptation (HDA) addresses the task of associating data not only across dissimilar domains but also described by different types of features. Inspired by the recent advances of neural networks and deep learning, we propose Transfer Neural Trees (TNT) which jointly solves cross-domain feature mapping, adaptation, and classification in a NN-based architecture. As the prediction layer in TNT, we further propose Transfer Neural Decision Forest (Transfer-NDF), which effectively adapts the neurons in TNT for adaptation by stochastic pruning. Moreover, to address semi-supervised HDA, a unique embedding loss term for preserving prediction and structural consistency between target-domain data is introduced into TNT. Experiments on classification tasks across features, datasets, and modalities successfully verify the effectiveness of our TNT.

[1]  Peter Kontschieder,et al.  Neural Decision Forests for Semantic Image Labelling , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Michael I. Jordan,et al.  Learning Transferable Features with Deep Adaptation Networks , 2015, ICML.

[3]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Trevor Darrell,et al.  Simultaneous Deep Transfer Across Domains and Tasks , 2015, ICCV.

[5]  Yuan Shi,et al.  Geodesic flow kernel for unsupervised domain adaptation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Wayne Ieee,et al.  Entropy Nets: From Decision Trees to Neural Networks , 1990 .

[7]  Trevor Darrell,et al.  Deep Domain Confusion: Maximizing for Domain Invariance , 2014, CVPR 2014.

[8]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[9]  Daumé,et al.  Frustratingly Easy Semi-Supervised Domain Adaptation , 2010 .

[10]  Tinne Tuytelaars,et al.  Unsupervised Visual Domain Adaptation Using Subspace Alignment , 2013, 2013 IEEE International Conference on Computer Vision.

[11]  Tat-Seng Chua,et al.  NUS-WIDE: a real-world web image database from National University of Singapore , 2009, CIVR '09.

[12]  Peter Kontschieder,et al.  Deep Neural Decision Forests , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[13]  Ivor W. Tsang,et al.  Learning with Augmented Features for Heterogeneous Domain Adaptation , 2012, ICML.

[14]  Chang Wang,et al.  Heterogeneous Domain Adaptation Using Manifold Alignment , 2011, IJCAI.

[15]  Tinne Tuytelaars,et al.  A Testbed for Cross-Dataset Analysis , 2014, ECCV Workshops.

[16]  Min Xiao,et al.  Semi-supervised Subspace Co-Projection for Multi-class Heterogeneous Domain Adaptation , 2015, ECML/PKDD.

[17]  Qiang Yang,et al.  Translated Learning: Transfer Learning across Different Feature Spaces , 2008, NIPS.

[18]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[19]  Philip S. Yu,et al.  Transfer Learning on Heterogenous Feature Spaces via Spectral Transformation , 2010, 2010 IEEE International Conference on Data Mining.

[20]  Ivor W. Tsang,et al.  Domain Adaptation via Transfer Component Analysis , 2009, IEEE Transactions on Neural Networks.

[21]  Trevor Darrell,et al.  What you saw is not what you get: Domain adaptation using asymmetric kernel transforms , 2011, CVPR 2011.

[22]  Qiang Yang,et al.  Heterogeneous Transfer Learning for Image Classification , 2011, AAAI.

[23]  Ivor W. Tsang,et al.  Learning With Augmented Features for Supervised and Semi-Supervised Heterogeneous Domain Adaptation , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Hal Daumé,et al.  Frustratingly Easy Domain Adaptation , 2007, ACL.

[25]  Chong-Wah Ngo,et al.  Semi-supervised Domain Adaptation with Subspace Learning for visual recognition , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Trevor Darrell,et al.  Adapting Visual Category Models to New Domains , 2010, ECCV.

[27]  G. Griffin,et al.  Caltech-256 Object Category Dataset , 2007 .

[28]  Min Xiao,et al.  Feature Space Independent Semi-Supervised Domain Adaptation via Kernel Matching , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Jinhui Tang,et al.  Weakly-Shared Deep Transfer Networks for Heterogeneous-Domain Knowledge Propagation , 2015, ACM Multimedia.

[30]  Ivor W. Tsang,et al.  Heterogeneous Domain Adaptation for Multiple Classes , 2014, AISTATS.

[31]  François Laviolette,et al.  Domain-Adversarial Neural Networks , 2014, ArXiv.

[32]  Trevor Darrell,et al.  Semi-supervised Domain Adaptation with Instance Constraints , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[33]  Gabriela Csurka,et al.  Assembling Heterogeneous Domain Adaptation Methods for Image Classification , 2014, CLEF.

[34]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[35]  Benno Stein,et al.  Cross-Language Text Classification Using Structural Correspondence Learning , 2010, ACL.

[36]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[37]  Yunde Jia,et al.  Cross-View Action Recognition over Heterogeneous Feature Spaces , 2013, 2013 IEEE International Conference on Computer Vision.

[38]  Trevor Darrell,et al.  Efficient Learning of Domain-invariant Image Representations , 2013, ICLR.

[39]  Victor S. Lempitsky,et al.  Unsupervised Domain Adaptation by Backpropagation , 2014, ICML.